j

[j @jc5qff]

@wangzhian8848 新疆暴乱的根源就是土耳其在背后支持

[brainstormity @brainstormity]

I just built Computer Use that’s cheaper, faster, and acts like a human 🖥️

Powered by @typesafeai’s JEV 1.14, using the new Image/Box feature.

It looks at the screen, decides what to do, then clicks and types like a real person.

⚡ Way cheaper than using an LLM
🧑 Acts like a human: sees the screen, picks an action, clicks or types it
📋 Full report of every step: the screenshot, the action it picked and why

Demo: I told it to open Wikipedia, search for an article about aliens, copy the link, and post a tweet with the link and some text.
- Cost: $0.0019
- Tokens: ~50,000

OPEN SOURCING SOON on my github 👀 (as always)

[j @jc5qff]

@zhu185178 我都用了 4 年了，为啥我一直没被封？我真的不知道你们到底是用它干了什么

[Davidzhu @DavidzhuLife]

遇到这种的你只管大胆的盯着看就行了，别怕被骂，她故意的。

[SuSu_酥酥👅 @NFT_Chen]

🔥厉害！DeepSeek V4.1 Flash 1017 无审查版正式放出！权重级彻底去除拒答，不是提示词破甲！

核心亮点：
🔹原生 FP8 + FP4 experts，drop-in 直接替换原模型

🔹1M 上下文 + Vision/Video + Tool Calling + Reasoning tiers 完整保留

🔹HarmBench 100% 合规（320/320 零拒绝），能力损���极小（MMLU 仅降约 3.9pp）

🔹无系统提示、无模板、无 LoRA、无 SFT，纯权重修改

🔹后续还会出 2.8bpw / NVFP4 版，专为 2x DGX Spark 优化

关键操作步骤：
1️⃣前往 HF 下载 dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8（需同意使用条款）

2️⃣用官方 inference 脚本转换 TP 布局：python https://t.co/SmjYdOnkFM –hf-ckpt-path .. –model-parallel 4 –expert-dtype fp4

3️⃣推荐采样：temperature=1.0、top_p=1.0、max_tokens≥256K

4️⃣用 vLLM / SGLang / 官方 https://t.co/Jo1ToktnSw 启动（需 FP8 GPU，如 H100/H200/B200）

5️⃣本地或云端部署后即可享受真正“不拒答”的智能��与编码体验

部署链接：https://t.co/JrTC8sMeP7

#DeepSeek #DeepSeekV41 #UncensoredAI #OpenSourceAI #LocalLLM #AIAgent #DGXSpark #FP8

[j @jc5qff]

@BossBear_0621 这傻逼真是个狗奴才

[j @jc5qff]

@wlzh 数据放进去，跟直接撒在大街上没有任何区别，甚至还不如🌚

[时光..... @nn_nici]

来用一句话总结一下这两集美

[Grirk @Grirku]

THIS IS A PURE FUCKING GOLDMINE

Anthropic just showed one of the cleanest Claude Code tricks.

Opus 5.5 writes the plan as a script, then sits idle at zero tokens while 12 cheap agents actually do the work.

Same task, two ways:
Opus solo was still at 49% and burning 231k tokens.
The swarm finished in 9:05 on 165k tokens 2× faster.

You launch it like this:

claude --model opus --swarm haiku,sonnet

Here’s the split:

→ Opus 5.5 writes plan.js and stops reading anything
→ 6× Haiku 5.5 audit every file in parallel
→ 4× Sonnet 5.5 patch each fix in its own isolated copy
→ 2× Haiku 5.5 cross-check (8 of 9 findings survive)

Opus only appears twice:
→ writing the plan
→ signing off on the verified fixes

Opus plans. Haiku scans. Sonnet ships.

JEV sits one layer down and resolves 3,767 micro-forks (which model, which lane, retry or stop) in code. Only the real splits ever reach Opus.

The full tree
> Opus 5.5 runs the main session on xhigh and writes the plan
> scan audits files on Haiku 5.5 ×6
> patch applies fixes on Sonnet 5.5 in isolated copies
> verify cross-checks on Haiku 5.5
> Opus only reads what survived, then signs off
> JEV handles deterministic forks in milliseconds

Paste the tree + this prompt into Claude Code ↓

Rebuild my Claude Code setup around this tree:

Run the main session on Opus 5.5 with effort xhigh and --swarm haiku,sonnet.
Have Opus write the plan as a script: scan on Haiku 5.5, patch on Sonnet 5.5 in isolated copies, verify on Haiku 5.5.
Let the phases overlap each finding moves forward as soon as its own stage finishes, no waiting for the batch.
Never surface raw agent output to the main session, only verified results.
Route deterministic forks (model choice, lane choice, retries) through JEV.
Show me every change as a diff first. No edits until I say go.

save it, it’ll come in handy.

[米开朗基杨 @CarsonYangk8s]

这个 opus 5.5 提示词牛逼，抵得上百万特效设计师👇

[j @jc5qff]

@Stargridcompass v4.1flsh token效率太低了，完成同样的任务最终的消耗和花费的时间绝对是更加聪明的opus 5.5 和 6.1sol更加高效，亲测过

[j @jc5qff]

@LannyTheClever @Sukiea1008 不用，安装好Codex CLI 登录后，直接在Claude Desktop 对话让他调用 它能帮你搞定一切，最终Codex额度多到用不完，可以把一些重活交给它

[j @jc5qff]

@hggvd393107 舔的更香了

[j @jc5qff]

@xiangning0 token效率太低了，我同样的一个图纸解密，丢给DeepSeek v4.1 flash 它一顿操作半小时还是以失败告终
然后回家换成了 6 astla 大概同样只画了 30分钟左右就成功了

[j @jc5qff]

@xingzengji codex桌面版其实更加好用，但是多任务调度管理没有claude强大，最主要痛点是模型太慢了，上下文太短，而且各种重复测试太他妈多了

[j @jc5qff]

@newbeeyu 哎，先去把英文学好吧，真的好丢人了🤦‍♂️

[j @jc5qff]

@vincent_ddup 不用这么费劲的

[j @jc5qff]

@Sukiea1008 max 20x

[j @jc5qff]

@xodud_rkd claude刚刚推出不久我就注册了。应该算是第一批的老用户了，一直都是中文对话，没改时区。没改地区，就正常使用。没有被封过一次号